INDEX

Explanations

references to medical examinations or investigations, particularly autopsies

oai_token-act-pair · gpt-3.5-turbo

terms related to autopsy and forensic examination processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atan

-0.94

å¥³

-0.77

TW

-0.76

Torrent

-0.73

 Mechdragon

-0.73

FUL

-0.72

unin

-0.68

arta

-0.64

HCR

-0.63

ateful

-0.63

POSITIVE LOGITS

ysis

1.02

 autopsy

0.95

 inquest

0.92

 coroner

0.87

 Canaver

0.86

mortem

0.81

etics

0.79

 dissect

0.79

 disse

0.78

 resusc

0.77

Activations Density 0.018%

references to medical examinations or investigations, particularly autopsies

terms related to autopsy and forensic examination processes

No Comments

No Known Activations